AI settings
Overview
This is where what the AI works with lives: access to the providers and the question of which model is used for which task. What the AI knows, by contrast, lives in the CompanyBrain.
Four tabs: Providers · Own & local models · Routing per task · Agents & prompts. The first three are an administrative matter; the fourth belongs to each individual user and is therefore always there.
One property matters more than any setting: models are not hard-coded. They come from a catalogue queried at the provider and refreshed regularly. A new model therefore appears by itself — without anybody having to ship a new release.
Core tasks
Set up access. For each provider you store an API key. It is stored encrypted and never shown again. Leaving the field empty keeps the stored key unchanged — the field is not a display field but an overwrite field.
Some providers allow a key from the server environment as a fallback. The list states where a key comes from: Key stored, From environment or No key.
Choose a default model. A default model can be set per provider, and one provider can be marked as the overall default.
Connect your own and local models. Providers without a fixed address require a base URL for your own resource. If it is missing, the list reports Address missing. This tab appears only if you hold the necessary permission.
Routing per task. The third tab decides which model handles which task. That is the lever for cost and quality: a short summary needs no model that a complex analysis would justify.
Maintain agents, skills and prompts. The fourth tab is the library of the AI assistant — the place where both are created, changed, shared and deleted. The assistant links to it from the menu behind the three dots.
Agents are preconfigured assistants: name, instruction, allowed tools, autonomy. Two rules govern what can be set:
- Without an allowed tool an agent is advisory only. Only with tools does the choice between
with confirmation and without asking appear.
- Acting without asking and publishing a writing agent are governance matters. Without the
permission the form does not offer the level, and publishing goes into approval first — the agent stays a draft until then.
Skills and prompts are text building blocks that can be inserted in the assistant's input bar. Some ship with the product; those are read-only because they are restored on every update. For your own version, create a new building block.
Visibility decides in both sections who sees the entry: Private stays with you, Team and Brand share it with others. Entries owned by others appear in the list but cannot be edited.
Fields in detail
| Field | Required | Values / format | What it does |
|---|---|---|---|
API key apiKey | yes | text | The provider's key. Stored encrypted and never shown again; entering it anew replaces it. It has monetary value — it incurs cost on your bill with the provider. |
Base address baseUrl | no | address | Where requests go. Empty means the provider's official address. Needed for self-hosted or local models; addresses on a private network are permitted only with explicit release, for security reasons. |
Default model defaultModel | no | a model from the catalogue | Which model is used when a use case names none. Models are not in the code: the catalogue is fetched from the provider and refreshed daily, so a new model does not wait for an update. |
Brand brandId | no | one of your brands | Which brand the access applies to. That way each brand can use its own contract. |
Default isDefault | no | yes/no | Which access is used when nothing else is chosen. |
Active active | no | yes/no | Whether the access is used. Off disables the AI functions that depend on it — they report that instead of quietly delivering nothing. |
Every run is recorded with consumption and cost. That is the only way to know at month's end what the money went on.
Settings & permissions
- Every tab hangs on its own permission. Providers and Routing per task require the AI
management permission, Own & local models the AI workspace governance one. Without the respective permission the tab is not there — not merely locked. Agents & prompts belongs to the user and needs no special permission; the page then opens straight into it.
- Keys cannot be read back. The display shows
••••••••. - The model catalogue expires and is refreshed. A provider whose catalogue cannot be retrieved
offers no models.
- The assistant additionally needs feature flags. Without
ai.gatewayandai.workspacethe
AI assistant is unavailable, even with a configured provider.
FAQ & troubleshooting
No models can be selected. Check the provider's access. Without a valid key the catalogue returns nothing.
A new model from the provider is missing. The catalogue is refreshed periodically. Refresh models fetches it immediately.
The assistant says it is not enabled. That is not a question for this page but for the feature flags — see System & feature flags.
I have forgotten the key. It cannot be read back here. Generate a new one at the provider and enter it.
I cannot edit an agent or building block. Then it is not yours: it was either shared by somebody else or came with the product. Create your own version instead.
My agent says "draft" although I chose "published". It uses a writing tool. Publication is waiting for approval by somebody holding the governance permission.